3.2 About the SQLcl MCP Server Tools

The SQLcl MCP Server exposes a set of tools that enhance the way AI applications interact with Oracle databases. By abstracting the SQLcl commands used for various database operations, these tools empower AI models to autonomously manage databases. This allows you to focus on strategic objectives instead of manual command-line interactions.

Additionally, the tools unlock sophisticated workflows through natural language interfaces, enabling AI systems to execute database demonstrations, manage large-scale data migrations, run complex analytical queries, and automate administrative tasks. Ultimately, the SQLcl MCP Server eliminates the need for direct manual input and allows AI applications to independently perform complex database operations that would have required significant technical expertise and effort.

Currently, the SQLcl MCP Server offers the following tools:

• list-connections: Discovers and lists all saved Oracle Database connections on your machine.
• connect: Establishes a connection to one of your specified named connections.
• disconnect: Terminates the current, active Oracle Database connection.
• run-sql: Executes standard SQL queries and PL/SQL code blocks against the connected database.
• run-sqlcl: Executes SQLcl-specific commands and extensions.
• schema-information: Provides detailed insights about the currently connected schema.
• context_retrieve: Retrieves relevant document context from compatible SQLcl RAG vector tables. Before using this tool, configure an embedding model and ingest documents using model ingest. For information about preparing documents and using retrieval in a RAG (Retrieval-Augmented Generation) workflow, see Using MODEL with Retrieval-Augmented Generation..
• annotation_generate: Creates annotations for tables and columns.
• skill_sync: Updates the set of available skills.
• request_status: Checks the current status of a previously submitted asynchronous request.